caffe-window搭建自己的小项目例子

手头有一个实际的视觉检测的项目，用的是caffe来分类，于是需要用caffe新建自己的项目的例子。在网上找了好久都没有找到合适的，于是自己开始弄。

1 首先是配置caffe的VC++目录中的include和库文件。配置include lib dll都是坑，而且还分debug和release两个版本。添加输入项目需要注意，而且需要把编译好的caffe.lib等等一系列东西拷贝到当前项目下。也就是caffe bulid文件夹下面的东西，包括caffe.lib 、libcaffe.lib、还有很多dll.

这个是debug_include配置图

这个是debug_lib配置图

这个是release_include配置图

这个是release_lib配置图

同时也需要在，项目属性页的链接器输入中，填写相应的lib，其中debug和release是不同的。以下是需要填写的相应lib

//debug
opencv_calib3d2413d.lib
opencv_contrib2413d.lib
opencv_core2413d.lib
opencv_features2d2413d.lib
opencv_flann2413d.lib
opencv_gpu2413d.lib
opencv_highgui2413d.lib
opencv_imgproc2413d.lib
opencv_legacy2413d.lib
opencv_ml2413d.lib
opencv_objdetect2413d.lib
opencv_ts2413d.lib
opencv_video2413d.lib
caffe.lib
libcaffe.lib
cudart.lib
cublas.lib
curand.lib
gflagsd.lib
libglog.lib
libopenblas.dll.a
libprotobuf.lib
leveldb.lib
hdf5.lib
hdf5_hl.lib
Shlwapi.lib
//release
opencv_calib3d2413.lib
opencv_contrib2413.lib
opencv_core2413.lib
opencv_features2d2413.lib
opencv_flann2413.lib
opencv_gpu2413.lib
opencv_highgui2413.lib
opencv_imgproc2413.lib
opencv_legacy2413.lib
opencv_ml2413.lib
opencv_objdetect2413.lib
opencv_ts2413.lib
opencv_video2413.lib
caffe.lib
libcaffe.lib
cudart.lib
cublas.lib
curand.lib
gflags.lib
libglog.lib
libopenblas.dll.a
libprotobuf.lib
leveldb.lib
lmdb.lib
hdf5.lib
hdf5_hl.lib
Shlwapi.lib

2 新建一个Classifier的c++类，其中头文件为

#include "stdafx.h"

#include <caffe/caffe.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <algorithm>
#include <iosfwd>
#include <memory>
#include <string>
#include <utility>
#include <vector>

#pragma once

using namespace caffe;  // NOLINT(build/namespaces)
using std::string;
//using namespace boost; 注意不需要添加这个

/* Pair (label, confidence) representing a prediction. */
typedef std::pair<string, float> Prediction;

class Classifier
{
public:
	Classifier(const string& model_file,
		const string& trained_file,
		const string& mean_file,
		const string& label_file);

	std::vector<Prediction> Classify(const cv::Mat& img, int N = 5);

	~Classifier();

private:
	void SetMean(const string& mean_file);

	std::vector<float> Predict(const cv::Mat& img);

	void WrapInputLayer(std::vector<cv::Mat>* input_channels);

	void Preprocess(const cv::Mat& img,
		std::vector<cv::Mat>* input_channels);

private:
	boost::shared_ptr<Net<float> > net_;
	cv::Size input_geometry_;
	int num_channels_;
	cv::Mat mean_;
	std::vector<string> labels_;
};

　　c++文件为

#include "stdafx.h"
#include "Classifier.h"

Classifier::Classifier(const string& model_file,
	const string& trained_file,
	const string& mean_file,
	const string& label_file) {
#ifdef CPU_ONLY
	Caffe::set_mode(Caffe::CPU);
#else
	Caffe::set_mode(Caffe::GPU);
#endif

	/* Load the network. */
	net_.reset(new Net<float>(model_file, TEST));
	net_->CopyTrainedLayersFrom(trained_file);

	CHECK_EQ(net_->num_inputs(), 1) << "Network should have exactly one input.";
	CHECK_EQ(net_->num_outputs(), 1) << "Network should have exactly one output.";

	Blob<float>* input_layer = net_->input_blobs()[0];
	num_channels_ = input_layer->channels();
	CHECK(num_channels_ == 3 || num_channels_ == 1)
		<< "Input layer should have 1 or 3 channels.";
	input_geometry_ = cv::Size(input_layer->width(), input_layer->height());

	/* Load the binaryproto mean file. */
	SetMean(mean_file);

	/* Load labels. */
	std::ifstream labels(label_file.c_str());
	CHECK(labels) << "Unable to open labels file " << label_file;
	string line;
	while (std::getline(labels, line))
		labels_.push_back(string(line));

	Blob<float>* output_layer = net_->output_blobs()[0];
	CHECK_EQ(labels_.size(), output_layer->channels())
		<< "Number of labels is different from the output layer dimension.";
}

static bool PairCompare(const std::pair<float, int>& lhs,
	const std::pair<float, int>& rhs) {
	return lhs.first > rhs.first;
}

/* Return the indices of the top N values of vector v. */
static std::vector<int> Argmax(const std::vector<float>& v, int N) {
	std::vector<std::pair<float, int> > pairs;
	for (size_t i = 0; i < v.size(); ++i)
		pairs.push_back(std::make_pair(v[i], static_cast<int>(i)));
	std::partial_sort(pairs.begin(), pairs.begin() + N, pairs.end(), PairCompare);

	std::vector<int> result;
	for (int i = 0; i < N; ++i)
		result.push_back(pairs[i].second);
	return result;
}

/* Return the top N predictions. */
std::vector<Prediction> Classifier::Classify(const cv::Mat& img, int N) {
	std::vector<float> output = Predict(img);

	N = std::min<int>(labels_.size(), N);
	std::vector<int> maxN = Argmax(output, N);
	std::vector<Prediction> predictions;
	for (int i = 0; i < N; ++i) {
		int idx = maxN[i];
		predictions.push_back(std::make_pair(labels_[idx], output[idx]));
	}

	return predictions;
}

/* Load the mean file in binaryproto format. */
void Classifier::SetMean(const string& mean_file) {
	BlobProto blob_proto;
	ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);

	/* Convert from BlobProto to Blob<float> */
	Blob<float> mean_blob;
	mean_blob.FromProto(blob_proto);
	CHECK_EQ(mean_blob.channels(), num_channels_)
		<< "Number of channels of mean file doesn't match input layer.";

	/* The format of the mean file is planar 32-bit float BGR or grayscale. */
	std::vector<cv::Mat> channels;
	float* data = mean_blob.mutable_cpu_data();
	for (int i = 0; i < num_channels_; ++i) {
		/* Extract an individual channel. */
		cv::Mat channel(mean_blob.height(), mean_blob.width(), CV_32FC1, data);
		channels.push_back(channel);
		data += mean_blob.height() * mean_blob.width();
	}

	/* Merge the separate channels into a single image. */
	cv::Mat mean;
	cv::merge(channels, mean);

	/* Compute the global mean pixel value and create a mean image
	* filled with this value. */
	cv::Scalar channel_mean = cv::mean(mean);
	mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
}

std::vector<float> Classifier::Predict(const cv::Mat& img) {
	Blob<float>* input_layer = net_->input_blobs()[0];
	input_layer->Reshape(1, num_channels_,
		input_geometry_.height, input_geometry_.width);
	/* Forward dimension change to all layers. */
	net_->Reshape();

	std::vector<cv::Mat> input_channels;
	WrapInputLayer(&input_channels);

	Preprocess(img, &input_channels);

	net_->Forward();

	/* Copy the output layer to a std::vector */
	Blob<float>* output_layer = net_->output_blobs()[0];
	const float* begin = output_layer->cpu_data();
	const float* end = begin + output_layer->channels();
	return std::vector<float>(begin, end);
}

/* Wrap the input layer of the network in separate cv::Mat objects
* (one per channel). This way we save one memcpy operation and we
* don't need to rely on cudaMemcpy2D. The last preprocessing
* operation will write the separate channels directly to the input
* layer. */
void Classifier::WrapInputLayer(std::vector<cv::Mat>* input_channels) {
	Blob<float>* input_layer = net_->input_blobs()[0];

	int width = input_layer->width();
	int height = input_layer->height();
	float* input_data = input_layer->mutable_cpu_data();
	for (int i = 0; i < input_layer->channels(); ++i) {
		cv::Mat channel(height, width, CV_32FC1, input_data);
		input_channels->push_back(channel);
		input_data += width * height;
	}
}

void Classifier::Preprocess(const cv::Mat& img,
	std::vector<cv::Mat>* input_channels) {
	/* Convert the input image to the input image format of the network. */
	cv::Mat sample;
	if (img.channels() == 3 && num_channels_ == 1)
		cv::cvtColor(img, sample, cv::COLOR_BGR2GRAY);
	else if (img.channels() == 4 && num_channels_ == 1)
		cv::cvtColor(img, sample, cv::COLOR_BGRA2GRAY);
	else if (img.channels() == 4 && num_channels_ == 3)
		cv::cvtColor(img, sample, cv::COLOR_BGRA2BGR);
	else if (img.channels() == 1 && num_channels_ == 3)
		cv::cvtColor(img, sample, cv::COLOR_GRAY2BGR);
	else
		sample = img;

	cv::Mat sample_resized;
	if (sample.size() != input_geometry_)
		cv::resize(sample, sample_resized, input_geometry_);
	else
		sample_resized = sample;

	cv::Mat sample_float;
	if (num_channels_ == 3)
		sample_resized.convertTo(sample_float, CV_32FC3);
	else
		sample_resized.convertTo(sample_float, CV_32FC1);

	cv::Mat sample_normalized;
	cv::subtract(sample_float, mean_, sample_normalized);

	/* This operation will write the separate BGR planes directly to the
	* input layer of the network because it is wrapped by the cv::Mat
	* objects in input_channels. */
	cv::split(sample_normalized, *input_channels);

	CHECK(reinterpret_cast<float*>(input_channels->at(0).data)
		== net_->input_blobs()[0]->cpu_data())
		<< "Input channels are not wrapping the input layer of the network.";
}

Classifier::~Classifier()
{
}

　　c++,文件来自于\caffe-master\examples\cpp_classification中的classification.cpp文件

3 直接编译后会出现的问题是F0519 14:54:12.494139 14504 layer_factory.hpp:77] Check failed: registry.count(t ype) == 1 (0 vs. 1) Unknown layer type: Input (known types: Input ),百度后发现是要加头文件！http://blog.****.net/fangjin_kl/article/details/50936952#0-tsina-1-63793-397232819ff9a47a7b7e80a40613cfe1

因此安装上面说的新建一个head.h

#include "caffe/common.hpp"
#include "caffe/layers/input_layer.hpp"
#include "caffe/layers/inner_product_layer.hpp"
#include "caffe/layers/dropout_layer.hpp"
#include "caffe/layers/conv_layer.hpp"
#include "caffe/layers/relu_layer.hpp"

#include "caffe/layers/pooling_layer.hpp"
#include "caffe/layers/lrn_layer.hpp"
#include "caffe/layers/softmax_layer.hpp"

namespace caffe
{

	extern INSTANTIATE_CLASS(InputLayer);
	extern INSTANTIATE_CLASS(InnerProductLayer);
	extern INSTANTIATE_CLASS(DropoutLayer);
	extern INSTANTIATE_CLASS(ConvolutionLayer);
	REGISTER_LAYER_CLASS(Convolution);
	extern INSTANTIATE_CLASS(ReLULayer);
	REGISTER_LAYER_CLASS(ReLU);
	extern INSTANTIATE_CLASS(PoolingLayer);
	REGISTER_LAYER_CLASS(Pooling);
	extern INSTANTIATE_CLASS(LRNLayer);
	REGISTER_LAYER_CLASS(LRN);
	extern INSTANTIATE_CLASS(SoftmaxLayer);
	REGISTER_LAYER_CLASS(Softmax);

}

注意上述网络可能不全，需要根据实际的网络添加层。参考

 #include<caffe/common.hpp>
 #include<caffe/proto/caffe.pb.h>
 #include<caffe/layers/batch_norm_layer.hpp>
 #include<caffe/layers/bias_layer.hpp>
 #include <caffe/layers/concat_layer.hpp>
 #include <caffe/layers/conv_layer.hpp>
 #include <caffe/layers/dropout_layer.hpp>
 #include<caffe/layers/input_layer.hpp>
 #include <caffe/layers/inner_product_layer.hpp>
 #include "caffe/layers/lrn_layer.hpp"
 #include <caffe/layers/pooling_layer.hpp>
 #include <caffe/layers/relu_layer.hpp>
 #include "caffe/layers/softmax_layer.hpp"
 #include<caffe/layers/scale_layer.hpp>
 namespace caffe
 {
     extern INSTANTIATE_CLASS(BatchNormLayer);
     extern INSTANTIATE_CLASS(BiasLayer);
     extern INSTANTIATE_CLASS(InputLayer);
     extern INSTANTIATE_CLASS(InnerProductLayer);
     extern INSTANTIATE_CLASS(DropoutLayer);
     extern INSTANTIATE_CLASS(ConvolutionLayer);
     REGISTER_LAYER_CLASS(Convolution);
     extern INSTANTIATE_CLASS(ReLULayer);
     REGISTER_LAYER_CLASS(ReLU);
     extern INSTANTIATE_CLASS(PoolingLayer);
     REGISTER_LAYER_CLASS(Pooling);
     extern INSTANTIATE_CLASS(LRNLayer);
     REGISTER_LAYER_CLASS(LRN);
     extern INSTANTIATE_CLASS(SoftmaxLayer);
     REGISTER_LAYER_CLASS(Softmax);
     extern INSTANTIATE_CLASS(ScaleLayer);
     extern INSTANTIATE_CLASS(ConcatLayer);

 }

4 出现的第二个问题是有些符号GLOG_NO_ABBREVIATED_SEVERITIES未定义，因此在项目属性页 c++预处理器中添加下面两个：

GLOG_NO_ABBREVIATED_SEVERITIES
_SCL_SECURE_NO_WARNINGS

5 同时需要把

#include <caffe/proto/caffe.pb.h>
#include "head.h"

这两个头文件放到stdafx.h中，必须放到里面。

6 编译通过后，编写测试分类的程序，首先加载caffermodle.

string model_file = "D:\\caffe\\caffe-master\\mypower\\deploy.prototxt";//prototxt 这个必须是depoly，这个是计算输出的类别概率
string trained_file = "D:\\caffe\\caffe-master\\mypower_iter_2000.caffemodel"; //这个是训练好的model
string mean_file = "D:\\caffe\\caffe-master\\mypower\\imagenet_mean.binaryproto";//这个是均值文件
string label_file ="D:\\caffe\\caffe-master\\mypower\\label.txt"; //这个是样本标签 ,如果两类，可以新建一个txt文件，里面写作如下

0 good
1 bad

定义一个指针  Classifier *classifier;
classifier = new Classifier(model_file, trained_file, mean_file, label_file);

分类程序：

   cv::Mat img(roiimage, 0);//加载图像
   //CHECK(!img.empty()) << "Unable to decode image " ;
   std::vector<Prediction> predictions = classifier->Classify(img);
   /* Print the top N predictions. */
   string precision_p0="";
   for (size_t i = 0; i < predictions.size()-1; ++i)//只输出了概率最大的那一类,通常就是第一类
   {
	Prediction p = predictions[i];
	precision_p0 = p.first;
	std::cout << std::fixed << std::setprecision(4) << p.second << " - \""
	<< p.first << "\"" << std::endl;
   }
   char firstc = precision_p0[0];
   if (firstc == '0')//第一类正样本 好的
   {
	//AfxMessageBox("good");
   }
   else //第二类负样本 存在缺陷
   {
	//AfxMessageBox("bad");
  }